Yu Chen

Yu Chen

Auto-generated profile, based on publicly available information

Yu Chen

School of Information Sciences and Engineering, Chongqing Jiaotong University, Chongqing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 June 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
QXQiao Xiao
Qiao Xiao
RLRen Li
Ren Li
JYJianxi Yang
Jianxi Yang
YCYu Chen
Yu Chen
SJShixin Jiang
Shixin Jiang
DWDi Wang
Di Wang

1 January 2023 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
PDF file
RLRen Li
Ren Li
QXQiao Xiao
Qiao Xiao
JYJianxi Yang
Jianxi Yang
HRHao Ren
Hao Ren
YCYu Chen
Yu Chen
In order to overcome the problems that the feature representation and classification effect of the existing methods need to be improved in complex contexts, this paper presents a novel few‐shot relation extraction approach via the entity feature enhancement and attention‐based prototypical network. The proposed model uses the pretrained RoBERTa model as the encoder while using the BiLSTM module for directional feature extraction. We further incorporate the entity feature enhancement module to improve the feature representation ability of the model. At last, the attention‐based prototypical network is used to predict relations. The experimental results show that the proposed method not only outperforms the baseline models on the datasets from the bridge inspection and health domains but also achieves competitive results on the FewRel dataset in the general domain.

31 October 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
RLRen Li
Ren Li
QXQiao Xiao
Qiao Xiao
JYJianxi Yang
Jianxi Yang
LZLuyi Zhang
Luyi Zhang
YCYu Chen
Yu Chen
The rapid development of pre-trained language models (PLMs) has significantly enhanced the performance of machine reading comprehension (MRC). Nevertheless, the traditional fine-tuning approaches necessitate extensive labeled data. MRC remains a challenging task in the few-shot settings or low-resource scenarios. This study proposes a novel few-shot MRC approach via post-training and answer span-oriented contrastive learning, termed MRC-PASCL. Specifically, in the post-training module, a novel noun-entity-aware data selection and generation strategy is proposed according to characteristics of MRC task and data, focusing on masking nouns and named entities in the context. In terms of fine-tuning, the proposed answer span-oriented contrastive learning manner selects spans around the golden answers as negative examples, and performs multi-task learning together with the standard MRC answer prediction task. Experimental results show that MRC-PASCL outperforms the PLMs-based baseline models and the 7B and 13B large language models (LLMs) cross most MRQA 2019 datasets. Further analyses show that our approach achieves better inference efficiency with lower computational resource requirement. The analysis results also indicate that the proposed method can better adapt to the domain-specific scenarios.

18 August 2023
Verified
Conference Paper
Closed access
ZZZiqian Zhang
Ziqian Zhang
YCYu Chen
Yu Chen
SLShengsheng Li
Shengsheng Li
SWShenliang Wang
Shenliang Wang
LLLi Li
Li Li
For current challenges of multi-dimensional data sharing and business integration of power transmission and transformation main equipment, this paper proposes a method for visual data fusion based on a digital twin in the power grid resource business center and conducts application verification finally. This paper is driven by the presentation and inter-action of digital twins, with scene interaction fusion as the main mode to construct twin scenes. Multiple information is embedded into the twin scenes as a supplement. For the cross-scale characteristics that need to be considered in large-scale geographic scenes and small-scale fine 3D models of power grid equipment, tile caching technology is used for map and satellite data fusion, the front-end and back-end separation of a four-layer logical architecture is used for 3D scene data fusion and free view video scene fusion is based on embedded camera positioning guided feature point texture. Finally, the above methods are applied and verified. The results showed that the above comprehensive technology can effectively solve the integration problem of facilities and surrounding environment, thereby meeting the actual production and operation needs.

1 January 2025 in International Journal of Intelligent Systems
Verified
Journal Article
Open access
RLRen Li
Ren Li
YCYu Chen
Yu Chen
HZHongyi Zhang
Hongyi Zhang
JYJianxi Yang
Jianxi Yang
QXQiao Xiao
Qiao Xiao
SJShixin Jiang
Shixin Jiang
Intelligent question answering over industrial databases is a challenging task due to the multicolumn context and complex questions. The existing methods need to be improved in terms of SQL generation accuracy. In this paper, we propose a question‐aware few‐shot Text‐to‐SQL approach based on the SDCUP pretrained model. Specifically, an attention‐based filtering approach is proposed to reduce the redundant information from multiple columns in the industrial database scenario. We further propose an operator semantics enhancement method to improve the ability of identifying complex conditions in queries. Experimental results on the industrial benchmarks in the fields of electric energy and structural inspection show that the proposed model outperforms the baseline models across all few‐shot settings.